SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]
- Default config:
anthropic_filemap.yaml swebench_submissions: Configs that were used for swebench submissionssweagent_0_7: Configs from SWE-agent 0.7, similar to the one used in the paperexotic: Various specific configurations that might be more of niche interesthuman: Demo/debug configs that have the human type commands and run without a LMdemo: Configs for demonstrations/talks- Configs for running with SWE-smith are at https://github.com/SWE-bench/SWE-smith/blob/main/agent/swesmith_infer.yaml
๐ Tutorial on adding custom tools ๐ For more information on config files, visit our documentation website.
You can also find the corresponding markdown files in the docs/ folder.